Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1460 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1500. Min Act: -0.0002

Data Index: 993813 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1489. Min Act: -0.0002

Data Index: 732133 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1133544 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1486. Min Act: -0.0002

Data Index: 1301336 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1276717 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1326. Min Act: -0.0002

Data Index: 1273723 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1494. Min Act: -0.0002

Data Index: 183091 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1370. Min Act: -0.0002

Data Index: 1201407 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1316. Min Act: -0.0002

Data Index: 158769 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1307. Min Act: -0.0001

Data Index: 172860 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1271. Min Act: -0.0001

Data Index: 792594 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1041. Min Act: -0.0002

Data Index: 13099 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1164004 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1246. Min Act: -0.0001

Data Index: 702444 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1241. Min Act: -0.0002

Data Index: 977268 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1247. Min Act: -0.0001

Data Index: 76462 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1080. Min Act: -0.0002

Data Index: 822275 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1289. Min Act: -0.0001

Data Index: 86487 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1185. Min Act: -0.0002

Data Index: 61982 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.1520. Min Range: -0.1520

Max Act: 0.1339. Min Act: -0.0002

Data Index: 696542 (C4 (Web Text))

Max Activating Token Index: 611